Skip to content
conftrace_
2026 EMNLP EMNLP 2026

How many raters do we need to recognize a bad translation via perplexity?

AbstractWe evaluated candidate translation pairs with various kinds of damage using perplexity assigned to them by LLMs to see how it holds up as a fluency and adequacy metric. We also explored how the discriminating power of perplexity can be improved by ensembling.

More from EMNLP 2026

All EMNLP 2026 papers →